cgato-nemo-12b-humanize_20284

developer_uid: cgato

submission_id: cgato-nemo-12b-humanize_20284_v5

model_name: cgato-nemo-12b-humanize_20284_v5

model_group: cgato/Nemo-12b-Humanize-

status: torndown

timestamp: 2025-01-08T15:58:58+00:00

num_battles: 8648

num_wins: 4460

celo_rating: 1276.17

family_friendly_score: 0.5871999999999999

family_friendly_standard_error: 0.006962702923434261

submission_type: basic

model_repo: cgato/Nemo-12b-Humanize-SFT-v0.1-E2

model_architecture: MistralForCausalLM

model_num_parameters: 12772111360.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.6191464213603101, 'latency_mean': 1.6150663352012635, 'latency_p50': 1.6071693897247314, 'latency_p90': 1.7871639251708984}, {'batch_size': 3, 'throughput': 1.1348814380673105, 'latency_mean': 2.6296006441116333, 'latency_p50': 2.6380399465560913, 'latency_p90': 2.898022270202637}, {'batch_size': 5, 'throughput': 1.38873402836332, 'latency_mean': 3.5905634820461274, 'latency_p50': 3.5705536603927612, 'latency_p90': 4.053906893730163}, {'batch_size': 6, 'throughput': 1.4420999568405335, 'latency_mean': 4.136779344081878, 'latency_p50': 4.125559091567993, 'latency_p90': 4.661339783668518}, {'batch_size': 8, 'throughput': 1.4987200120389164, 'latency_mean': 5.306325868368149, 'latency_p50': 5.32612681388855, 'latency_p90': 5.939566135406494}, {'batch_size': 10, 'throughput': 1.560255174221093, 'latency_mean': 6.373362271785736, 'latency_p50': 6.405414938926697, 'latency_p90': 7.212221455574036}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: cgato-nemo-12b-humanize_20284_v5

is_internal_developer: False

language_model: cgato/Nemo-12b-Humanize-SFT-v0.1-E2

model_size: 13B

ranking_group: single

throughput_3p7s: 1.41

us_pacific_date: 2025-01-08

win_ratio: 0.5157261794634598

generation_params: {'temperature': 0.7, 'top_p': 0.9, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.01, 'frequency_penalty': 0.01, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', 'truncate_by_message': True}

Resubmit model

Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name cgato-nemo-12b-humanize-20284-v5-mkmlizer
Waiting for job on cgato-nemo-12b-humanize-20284-v5-mkmlizer to finish
cgato-nemo-12b-humanize-20284-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cgato-nemo-12b-humanize-20284-v5-mkmlizer: ║     _____            __           __                                ║
cgato-nemo-12b-humanize-20284-v5-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cgato-nemo-12b-humanize-20284-v5-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cgato-nemo-12b-humanize-20284-v5-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cgato-nemo-12b-humanize-20284-v5-mkmlizer: ║       /___/                                                         ║
cgato-nemo-12b-humanize-20284-v5-mkmlizer: ║                                                                     ║
cgato-nemo-12b-humanize-20284-v5-mkmlizer: ║  Version: 0.11.12                                                   ║
cgato-nemo-12b-humanize-20284-v5-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cgato-nemo-12b-humanize-20284-v5-mkmlizer: ║  https://mk1.ai                                                     ║
cgato-nemo-12b-humanize-20284-v5-mkmlizer: ║                                                                     ║
cgato-nemo-12b-humanize-20284-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
cgato-nemo-12b-humanize-20284-v5-mkmlizer: ║  belonging to:                                                      ║
cgato-nemo-12b-humanize-20284-v5-mkmlizer: ║                                                                     ║
cgato-nemo-12b-humanize-20284-v5-mkmlizer: ║  Chai Research Corp.                                                ║
cgato-nemo-12b-humanize-20284-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cgato-nemo-12b-humanize-20284-v5-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
cgato-nemo-12b-humanize-20284-v5-mkmlizer: ║                                                                     ║
cgato-nemo-12b-humanize-20284-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cgato-nemo-12b-humanize-20284-v5-mkmlizer: Downloaded to shared memory in 33.399s
cgato-nemo-12b-humanize-20284-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpofx10mpb, device:0
cgato-nemo-12b-humanize-20284-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cgato-nemo-12b-humanize-20284-v5-mkmlizer: quantized model in 35.323s
cgato-nemo-12b-humanize-20284-v5-mkmlizer: Processed model cgato/Nemo-12b-Humanize-SFT-v0.1-E2 in 68.722s
cgato-nemo-12b-humanize-20284-v5-mkmlizer: creating bucket guanaco-mkml-models
cgato-nemo-12b-humanize-20284-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cgato-nemo-12b-humanize-20284-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cgato-nemo-12b-humanize-20284-v5
cgato-nemo-12b-humanize-20284-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cgato-nemo-12b-humanize-20284-v5/config.json
cgato-nemo-12b-humanize-20284-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cgato-nemo-12b-humanize-20284-v5/special_tokens_map.json
cgato-nemo-12b-humanize-20284-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cgato-nemo-12b-humanize-20284-v5/tokenizer_config.json
cgato-nemo-12b-humanize-20284-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cgato-nemo-12b-humanize-20284-v5/tokenizer.json
cgato-nemo-12b-humanize-20284-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/cgato-nemo-12b-humanize-20284-v5/flywheel_model.0.safetensors
cgato-nemo-12b-humanize-20284-v5-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 31.78it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 53.89it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 47.06it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:07, 44.98it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 46.85it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 45.76it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:06, 45.93it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 51.36it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 48.13it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 37.44it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:07, 37.77it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:06, 42.10it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:06, 41.93it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 42.39it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:05, 46.92it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:05, 45.56it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:05, 45.25it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:04, 51.38it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:05, 43.86it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:05, 43.09it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:04, 47.72it/s]
Loading 0:  36%|███▌      | 131/363 [00:02<00:04, 47.79it/s]
Loading 0:  37%|███▋      | 136/363 [00:03<00:05, 41.12it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 36.35it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:05, 36.67it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 35.46it/s]
Loading 0:  43%|████▎     | 157/363 [00:03<00:04, 42.35it/s]
Loading 0:  45%|████▍     | 163/363 [00:03<00:04, 43.46it/s]
Loading 0:  46%|████▋     | 168/363 [00:03<00:04, 43.43it/s]
Loading 0:  48%|████▊     | 175/363 [00:03<00:03, 48.65it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:03, 47.48it/s]
Loading 0:  51%|█████     | 186/363 [00:04<00:03, 45.63it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 50.29it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 47.77it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 47.33it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:02, 51.79it/s]
Loading 0:  60%|█████▉    | 217/363 [00:04<00:02, 49.34it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:03, 38.62it/s]
Loading 0:  63%|██████▎   | 228/363 [00:05<00:03, 38.46it/s]
Loading 0:  64%|██████▍   | 233/363 [00:05<00:03, 40.35it/s]
Loading 0:  66%|██████▌   | 238/363 [00:05<00:03, 41.21it/s]
Loading 0:  67%|██████▋   | 243/363 [00:05<00:02, 42.29it/s]
Loading 0:  68%|██████▊   | 248/363 [00:05<00:03, 33.68it/s]
Loading 0:  70%|██████▉   | 253/363 [00:05<00:02, 36.69it/s]
Loading 0:  71%|███████   | 258/363 [00:06<00:02, 36.06it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 40.04it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 41.67it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:02, 43.77it/s]
Loading 0:  77%|███████▋  | 279/363 [00:06<00:01, 45.27it/s]
Loading 0:  78%|███████▊  | 284/363 [00:06<00:02, 38.80it/s]
Loading 0:  80%|████████  | 292/363 [00:06<00:01, 47.06it/s]
Loading 0:  82%|████████▏ | 298/363 [00:06<00:01, 44.38it/s]
Loading 0:  83%|████████▎ | 303/363 [00:06<00:01, 44.97it/s]
Loading 0:  85%|████████▍ | 308/363 [00:13<00:21,  2.59it/s]
Loading 0:  86%|████████▌ | 312/363 [00:13<00:15,  3.30it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:07,  5.38it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:05,  7.33it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:03,  9.33it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 13.20it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:01, 16.55it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 19.95it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 25.95it/s]
Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 28.86it/s]
                                                            
Job cgato-nemo-12b-humanize-20284-v5-mkmlizer completed after 93.83s with status: succeeded
Stopping job with name cgato-nemo-12b-humanize-20284-v5-mkmlizer
Pipeline stage MKMLizer completed in 94.45s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cgato-nemo-12b-humanize-20284-v5
Waiting for inference service cgato-nemo-12b-humanize-20284-v5 to be ready
Inference service cgato-nemo-12b-humanize-20284-v5 ready after 351.58174419403076s
Pipeline stage MKMLDeployer completed in 352.09s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1442174911499023s
Received healthy response to inference request in 1.3134479522705078s
Received healthy response to inference request in 1.6497061252593994s
Received healthy response to inference request in 1.8197834491729736s
Received healthy response to inference request in 1.6479527950286865s
5 requests
0 failed requests
5th percentile: 1.3803489208221436
10th percentile: 1.4472498893737793
20th percentile: 1.5810518264770508
30th percentile: 1.648303461074829
40th percentile: 1.6490047931671143
50th percentile: 1.6497061252593994
60th percentile: 1.7177370548248292
70th percentile: 1.7857679843902587
80th percentile: 1.8846702575683594
90th percentile: 2.014443874359131
95th percentile: 2.0793306827545166
99th percentile: 2.131240129470825
mean time: 1.715021562576294
Pipeline stage StressChecker completed in 9.77s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.67s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.63s
Shutdown handler de-registered
cgato-nemo-12b-humanize_20284_v5 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 2678.99s
Shutdown handler de-registered
cgato-nemo-12b-humanize_20284_v5 status is now inactive due to auto deactivation removed underperforming models
cgato-nemo-12b-humanize_20284_v5 status is now torndown due to DeploymentManager action